LAM-PINN clusters PDE tasks via learning-affinity metrics and uses modular subnetworks to cut MSE by 19.7x on unseen tasks while using only 10% of conventional PINN training iterations.
One-shot transfer learn- ing of physics-informed neural networks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Chebyshev polynomial surrogates enable one-shot closed-form adaptation of PINNs for a broader class of nonlinear ODEs and PDEs by decomposing them into linear subproblems.
Pi-PINN learns transferable physics-informed representations and solves known or unseen PDEs via closed-form pseudoinverse head adaptation, achieving 100-1000x faster predictions and 10-100x lower error than standard PINNs or data-driven models even with minimal training samples.
RealDiffusion uses heat diffusion as a dissipative prior and a region-aware stochastic process inside a training-free physics-informed attention mechanism to improve multi-character coherence while preserving narrative dynamism in sequential image generation.
citing papers explorer
-
Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks
LAM-PINN clusters PDE tasks via learning-affinity metrics and uses modular subnetworks to cut MSE by 19.7x on unseen tasks while using only 10% of conventional PINN training iterations.
-
Chebyshev-Augmented One-Shot Transfer Learning for PINNs on Nonlinear Differential Equations
Chebyshev polynomial surrogates enable one-shot closed-form adaptation of PINNs for a broader class of nonlinear ODEs and PDEs by decomposing them into linear subproblems.
-
Transferable Physics-Informed Representations via Closed-Form Head Adaptation
Pi-PINN learns transferable physics-informed representations and solves known or unseen PDEs via closed-form pseudoinverse head adaptation, achieving 100-1000x faster predictions and 10-100x lower error than standard PINNs or data-driven models even with minimal training samples.
-
RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation
RealDiffusion uses heat diffusion as a dissipative prior and a region-aware stochastic process inside a training-free physics-informed attention mechanism to improve multi-character coherence while preserving narrative dynamism in sequential image generation.